ASH: Agents that Self-Hone via Embodied Learning

Computer Science > Artificial Intelligence [Submitted on 14 May 2026] ASH: Agents that Self-Hone via Embodied Learning Benjamin Schneider, Xavier Schneider, Victor Zhong, Sun Sun Long-horizon embodied tasks remain a fundamental challenge in AI, as current methods rely on hand-engineered rewards or action-labeled demonstrations, neither of which scales. We introduce ASH, an agentic system that learns an embodied policy from unlabeled, noisy internet video, without reward shaping or expert annotation. ASH follows a self-improvement loop; when it gets stuck, ASH learns an Inverse Dynamics Model (IDM) from its own trajectories, and uses its IDM to extract supervision from relevant internet video. ASH uses unsupervised learning to identify key moments from large-scale internet video and retains them as long-term memory -- allowing it to tackle long-horizon problems. We evaluate ASH on two complementary environments demanding multi-hour planning: Pokemon Emerald, a turn-based RPG, and The Legend of Zelda: The Minish Cap, a real-time action-adventure game. In both games, behavioral cloning, retrieval-augmented and zero-shot foundation-model baselines plateau, while ASH sustains progression across our 8-hour evaluation. ASH reaches an average of 11.2/12 milestones in Pokemon Emerald and 9.9/12 in Legend of Zelda, while the strongest baseline gets stuck in both environments at an average of 6.5/12 and 6.0/12 milestones, respectively. We demonstrate that self-improving agents are a scalable recipe for long-horizon embodied learning. Subjects: Artificial Intelligence (cs.AI); Machine Learning (cs.LG) Cite as: arXiv:2605.14211 [cs.AI]   (or arXiv:2605.14211v1 [cs.AI] for this version)   https://doi.org/10.48550/arXiv.2605.14211 Focus to learn more Submission history From: Benjamin Schneider [view email] [v1] Thu, 14 May 2026 00:10:12 UTC (10,330 KB) Access Paper: view license Current browse context: cs.AI < prev   |   next > new | recent | 2026-05 Change to browse by: cs cs.LG References & Citations NASA ADS Google Scholar Semantic Scholar Export BibTeX Citation Bookmark Bibliographic Tools Bibliographic and Citation Tools Bibliographic Explorer Toggle Bibliographic Explorer (What is the Explorer?) Connected Papers Toggle Connected Papers (What is Connected Papers?) Litmaps Toggle Litmaps (What is Litmaps?) scite.ai Toggle scite Smart Citations (What are Smart Citations?) Code, Data, Media Demos Related Papers About arXivLabs Which authors of this paper are endorsers? | Disable MathJax (What is MathJax?)